Expert(Sto) Return Avg: 5926.18, std: 124.56 # retrained by Yufei on July 17
array([5926.179, 5730.677, 5824.137, 5955.398, 5847.839, 6066.736,
       5706.077, 6105.023, 5927.851, 5927.464, 6050.575, 6162.145,
       6043.106, 5888.204, 5999.199, 5701.368, 6121.578, 5922.609,
       5877.748, 6044.576, 5977.024, 6041.073, 6080.149, 5890.946,
       5928.336, 5914.364, 5925.36 , 5944.162, 5971.436, 5997.144,
       5805.856, 5923.695, 5842.542, 5970.315, 5723.259, 5949.78 ,
       6146.484, 5984.89 , 5841.663, 5960.484, 5700.377, 5696.356,
       5890.842, 5784.999, 5955.16 , 5949.988, 5641.807, 5986.947,
       6136.71 , 6118.511, 5846.73 , 6042.562, 5944.697, 5787.549,
       6102.113, 5956.218, 5979.683, 5969.493, 5816.752, 5685.732,
       5871.238, 5883.844, 6048.18 , 5831.78 ])
Expert(Det) Return Avg: 6343.46, std: 804.67
array([6503.015, 6448.222, 6421.122, 6604.638, 6433.999, 6666.262,
       6441.027, 6533.571, 6466.512, 6386.295, 6577.331, 3818.065,
       6478.319, 6401.348, 6654.926, 6655.391, 6251.376, 6540.992,
       6389.508, 6461.423, 6264.928, 6552.596, 6503.469, 6258.903,
       6405.709, 6547.44 , 6547.254, 6543.118, 6749.464, 6483.46 ,
       6343.175, 6595.628, 6371.882,  611.278, 6561.999, 6552.76 ,
       6445.918, 6429.536, 6464.359, 6624.338, 5961.252, 6582.726,
       6318.72 , 6496.42 , 6384.581, 6577.697, 6407.099, 6346.082,
       6383.562, 6504.818, 6576.425, 6560.476, 6706.401, 6475.385,
       6597.345, 6487.816, 6455.082, 6446.894, 6605.802, 6255.455,
       6187.777, 6626.842, 6486.044, 6560.39 ])
ordereddict([('seed', 233), ('cuda', -1), ('env', ordereddict([('env_name', 'AntFH-v0'), ('T', 1000)])), ('sac', ordereddict([('epochs', 3000), ('log_step_interval', 5000), ('update_every', 50), ('update_num', 1), ('random_explore_episodes', 10), ('batch_size', 100), ('lr', 0.001), ('alpha', 0.2), ('automatic_alpha_tuning', False), ('buffer_size', 1000000), ('num_test_episodes', 10)])), ('expert', ordereddict([('samples_episode', 64)])), ('launching_env', 'ant'), ('_hidden_keys', []), ('exp_cnt', 6), ('exp_name', '7-16-sac-samples_2020_07_16_20_24_30_0007')])